Minirecord/Mini_msft
08
1{2 "_attn_implementation": "eager",3 "_name_or_path": "Minirecord/Mini_llama13b_test123",4 "architectures": [5 "LlamaForCausalLM"6 ],7 "attention_bias": false,8 "bos_token_id": 1,9 "eos_token_id": 2,10 "hidden_act": "silu",11 "hidden_size": 5120,12 "initializer_range": 0.02,13 "intermediate_size": 13824,14 "max_position_embeddings": 4096,15 "model_type": "llama",16 "num_attention_heads": 40,17 "num_hidden_layers": 40,18 "num_key_value_heads": 40,19 "pad_token_id": 0,20 "pretraining_tp": 1,21 "rms_norm_eps": 1e-06,22 "rope_scaling": null,23 "rope_theta": 10000.0,24 "tie_word_embeddings": false,25 "torch_dtype": "bfloat16",26 "transformers_version": "4.34.1",27 "use_cache": false,28 "vocab_size": 4633629}30 